
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import math
from sklearn.model_selection import train_test_split
from pandas_profiling import ProfileReport
%matplotlib inline
import plotly.express as px
from sklearn.metrics import accuracy_score, confusion_matrix, roc_curve, auc

pd.set_option('display.max_columns', None)


df = pd.read_csv("C:/Users/victo/Documents/NUCLIOMESTRADO/heart_disease_project_data/heart_disease_data.csv")

df


df.info(verbose=True)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 319795 entries, 0 to 319794
Data columns (total 20 columns):
 #   Column                      Non-Null Count   Dtype  
---  ------                      --------------   -----  
 0   HeartDisease                319795 non-null  object 
 1   BMI                         319795 non-null  float64
 2   Smoking                     319795 non-null  object 
 3   AlcoholDrinking             212984 non-null  object 
 4   Stroke                      318683 non-null  object 
 5   PhysicalHealth              319795 non-null  float64
 6   MentalHealth                319795 non-null  float64
 7   DiffWalking                 319795 non-null  object 
 8   Sex                         319795 non-null  object 
 9   AgeCategory                 319795 non-null  object 
 10  Race                        319795 non-null  object 
 11  Diabetic                    319795 non-null  object 
 12  PhysicalActivity            319795 non-null  object 
 13  GenHealth                   319795 non-null  object 
 14  SleepTime                   319795 non-null  float64
 15  Asthma                      319795 non-null  object 
 16  KidneyDisease               319795 non-null  object 
 17  SkinCancer                  319446 non-null  object 
 18  HeartDisease_FamilyHistory  35263 non-null   object 
 19  State                       319795 non-null  object 
dtypes: float64(4), object(16)
memory usage: 48.8+ MB


 df.shape

(319795, 20)


df.columns

Index(['HeartDisease', 'BMI', 'Smoking', 'AlcoholDrinking', 'Stroke',
       'PhysicalHealth', 'MentalHealth', 'DiffWalking', 'Sex', 'AgeCategory',
       'Race', 'Diabetic', 'PhysicalActivity', 'GenHealth', 'SleepTime',
       'Asthma', 'KidneyDisease', 'SkinCancer', 'HeartDisease_FamilyHistory',
       'State'],
      dtype='object')


numeric_features = df.select_dtypes(include=[np.number])
numeric_features.columns

Index(['BMI', 'PhysicalHealth', 'MentalHealth', 'SleepTime'], dtype='object')


categorical_features = df.select_dtypes(include=[object])
categorical_features.columns

Index(['HeartDisease', 'Smoking', 'AlcoholDrinking', 'Stroke', 'DiffWalking',
       'Sex', 'AgeCategory', 'Race', 'Diabetic', 'PhysicalActivity',
       'GenHealth', 'Asthma', 'KidneyDisease', 'SkinCancer',
       'HeartDisease_FamilyHistory', 'State'],
      dtype='object')


df.duplicated().sum()

254


#drop duplicates
df.drop_duplicates(inplace=True)


df.describe(include=['object']).T


df.isnull().sum()

HeartDisease                       0
BMI                                0
Smoking                            0
AlcoholDrinking               106753
Stroke                          1112
PhysicalHealth                     0
MentalHealth                       0
DiffWalking                        0
Sex                                0
AgeCategory                        0
Race                               0
Diabetic                           0
PhysicalActivity                   0
GenHealth                          0
SleepTime                          0
Asthma                             0
KidneyDisease                      0
SkinCancer                       349
HeartDisease_FamilyHistory    284280
State                              0
dtype: int64


df.isnull().sum()/len(df)*100

HeartDisease                   0.000000
BMI                            0.000000
Smoking                        0.000000
AlcoholDrinking               33.408232
Stroke                         0.347999
PhysicalHealth                 0.000000
MentalHealth                   0.000000
DiffWalking                    0.000000
Sex                            0.000000
AgeCategory                    0.000000
Race                           0.000000
Diabetic                       0.000000
PhysicalActivity               0.000000
GenHealth                      0.000000
SleepTime                      0.000000
Asthma                         0.000000
KidneyDisease                  0.000000
SkinCancer                     0.109219
HeartDisease_FamilyHistory    88.965109
State                          0.000000
dtype: float64


import missingno as msno
msno.bar(df)
plt.show()


def categorical_feature_func(df, categorical_features):
    num_features = len(categorical_features)
    plt.figure(figsize=(25, 20))

    for i, feature in enumerate(categorical_features, 1):
        plt.subplot(4, 4, i)
        sns.set(palette='Paired')
        sns.set_style("ticks")
        ax = sns.countplot(x=feature, data=df)
        ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha="right")

    plt.tight_layout()
    plt.show()

categorical_feature_func(df, categorical_features)


numeric_features = df.select_dtypes(include=[np.number])

plt.figure(figsize = (25,15))
for i, feature in enumerate(numeric_features.columns):
    plt.subplot(2,2,i + 1)
    sns.set(palette='dark')
    sns.set_style("ticks")
    sns.histplot(df[feature],kde=True)
    plt.xlabel(feature)
    plt.ylabel("Count")


df['HeartDisease']= df['HeartDisease'].replace(['Yes', 'No'] , [1,0])


plt.figure(figsize = (10, 6))
# Configurar fundo branco
plt.style.use("seaborn-v0_8-whitegrid")

# Proporção de doenças cardíacas a partir dos dados
plt.pie(x=df['HeartDisease'].value_counts(),
        autopct='%1.3f%%',
        labels=df['HeartDisease'].value_counts().index,
        colors=['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728'],
        wedgeprops={'linewidth': 1, 'edgecolor': 'white'})

# Configurar título e legenda
plt.title('Proporção de doenças cardíacas')
plt.legend()

# Ajustar layout para melhor aparência
plt.tight_layout()

# Exibir o gráfico
plt.show()


pd.set_option('display.max_rows', None)
df['BMI'].describe()

count    319541.000000
mean         28.328993
std           6.371116
min          12.020000
25%          24.030000
50%          27.340000
75%          31.450000
max         119.000000
Name: BMI, dtype: float64


# Criar o gráfico de dispersão
fig = px.scatter(df, x="BMI", y="SleepTime")

# Exibir o gráfico
fig.show()


# Verificando valores vazios na coluna 'SkinCancer'
df['SkinCancer'].isna().sum()

349


# Remover linhas com valores vazios na coluna 'SkinCancer'
df.dropna(subset=['SkinCancer'], inplace=True)


# Verificando valores vazios na coluna 'Stroke'
df['Stroke'].isna().sum()

1111


# Remover linhas com valores vazios na coluna 'Stroke'
df.dropna(subset=['Stroke'], inplace=True)


import plotly.express as px

def heart_Disease_Func(data, column, count=True):
    unique_values = data[column].unique()
    null_count = data[column].isnull().sum()
    value_counts = data[column].value_counts()
    
    print(f'Quantidade de valores únicos: {len(unique_values)}')
    print(f'\nQuais são os valores únicos: {unique_values}')
    print(f'\nQuantidade de valores nulos: {null_count}')
    print(f'\nQuantidade por opção: \n{value_counts}')
    
    if count:
        fig = px.histogram(data, x=column, color='HeartDisease', barmode='group')
        fig.show()
    else:
        fig = px.histogram(data, x=column, marginal='kde')
        fig.show()


heart_Disease_Func(df, 'HeartDisease_FamilyHistory')

Quantidade de valores únicos: 3

Quais são os valores únicos: ['No' nan 'Yes']

Quantidade de valores nulos: 282992

Quantidade por opção: 
No     31856
Yes     3233
Name: HeartDisease_FamilyHistory, dtype: int64


heart_Disease_Func(df, 'SleepTime')

Quantidade de valores únicos: 24

Quais são os valores únicos: [ 5.  7.  8.  6. 12.  4.  9. 10. 15.  3.  2.  1. 16. 18. 14. 20. 11. 13.
 17. 24. 19. 21. 22. 23.]

Quantidade de valores nulos: 0

Quantidade por opção: 
7.0     97164
8.0     97066
6.0     66388
5.0     19098
9.0     15972
10.0     7762
4.0      7712
12.0     2196
3.0      1981
2.0       786
1.0       544
11.0      415
14.0      243
16.0      236
15.0      189
18.0      102
13.0       95
20.0       64
24.0       30
17.0       21
22.0        9
19.0        3
23.0        3
21.0        2
Name: SleepTime, dtype: int64


heart_Disease_Func(df, 'Race')

Quantidade de valores únicos: 6

Quais são os valores únicos: ['White' 'Black' 'Asian' 'American Indian/Alaskan Native' 'Other'
 'Hispanic']

Quantidade de valores nulos: 0

Quantidade por opção: 
White                             243825
Hispanic                           27317
Black                              22846
Other                              10887
Asian                               8029
American Indian/Alaskan Native      5177
Name: Race, dtype: int64


heart_Disease_Func(df, 'AgeCategory')

Quantidade de valores únicos: 14

Quais são os valores únicos: ['55-59' '80 or older' '65-69' '75-79' '40-44' '70-74' '60-64' '50-54'
 '45-49' '18-24' '35-39' '30-34' '25-29' '0']

Quantidade de valores nulos: 0

Quantidade por opção: 
65-69          33965
60-64          33485
70-74          30904
55-59          29589
50-54          25210
80 or older    24063
45-49          21662
75-79          21383
18-24          20959
40-44          20900
35-39          20429
30-34          18627
25-29          16847
0                 58
Name: AgeCategory, dtype: int64


heart_Disease_Func(df, 'MentalHealth')

Quantidade de valores únicos: 31

Quais são os valores únicos: [30.  0.  2.  5. 15.  8.  4.  3. 10. 14. 20.  1.  7. 24.  9. 28. 16. 12.
 25. 17. 18. 21. 29.  6. 22. 13. 23. 27. 26. 11. 19.]

Quantidade de valores nulos: 0

Quantidade por opção: 
0.0     204227
30.0     17297
2.0      16417
5.0      14088
10.0     10464
3.0      10411
15.0      9845
1.0       9242
7.0       5505
20.0      5397
4.0       5355
14.0      2042
25.0      1945
6.0       1504
8.0       1091
12.0       755
28.0       509
21.0       350
29.0       316
18.0       211
9.0        203
16.0       151
17.0       127
27.0       125
13.0       110
22.0        98
11.0        83
23.0        67
24.0        66
26.0        59
19.0        21
Name: MentalHealth, dtype: int64


heart_Disease_Func(df, 'PhysicalHealth')

Quantidade de valores únicos: 31

Quais são os valores únicos: [ 3.  0. 20. 28.  6. 15.  5. 30.  7.  1.  2. 21.  4. 10. 14. 18.  8. 25.
 16. 29. 27. 17. 24. 12. 23. 26. 22. 19.  9. 13. 11.]

Quantidade de valores nulos: 0

Quantidade por opção: 
0.0     225304
30.0     19424
2.0      14808
1.0      10436
3.0       8586
5.0       7575
10.0      5425
15.0      4990
7.0       4605
4.0       4443
20.0      3197
14.0      2878
6.0       1265
25.0      1156
8.0        919
21.0       626
12.0       604
28.0       444
29.0       203
9.0        180
18.0       167
16.0       135
27.0       124
17.0       109
13.0        91
22.0        89
11.0        84
24.0        67
26.0        66
23.0        46
19.0        35
Name: PhysicalHealth, dtype: int64


df.AgeCategory.value_counts()

65-69          33965
60-64          33485
70-74          30904
55-59          29589
50-54          25210
80 or older    24063
45-49          21662
75-79          21383
18-24          20959
40-44          20900
35-39          20429
30-34          18627
25-29          16847
0                 58
Name: AgeCategory, dtype: int64


df['AgeCategory'].unique()

array(['55-59', '80 or older', '65-69', '75-79', '40-44', '70-74',
       '60-64', '50-54', '45-49', '18-24', '35-39', '30-34', '25-29', '0'],
      dtype=object)


df.drop(df[df['AgeCategory'] == '0'].index, inplace=True)


# Categorizing Age Groups in DataFrame
df['AgeCategory']=df['AgeCategory'].replace(['18-24','25-29','30-34'],'Jovem')
df['AgeCategory']=df['AgeCategory'].replace(['35-39','40-44','45-49','50-54'],'Adulto')
df['AgeCategory']=df['AgeCategory'].replace(['55-59','60-64','65-69','70-74'],'Idoso')
df['AgeCategory']=df['AgeCategory'].replace(['75-79','80 or older'],'Velho')


# Definir a ordem específica das categorias
order = ['Jovem', 'Adulto', 'Idoso', 'Velho']

# Criar um dicionário mapeando cada categoria para seu valor ordinal
mapping = {category: i for i, category in enumerate(order)}

# Aplicar a codificação ordinal na coluna 'GenHealth'
df['AgeCategory'] = df['AgeCategory'].map(mapping)


df['AgeCategory'].unique()

array([2, 3, 1, 0], dtype=int64)


import plotly.express as px

# Agrupar por 'AgeCategory' e 'HeartDisease' e contar ocorrências
data = df.groupby(['AgeCategory', 'HeartDisease']).size().unstack()

# Configurar cores
cores = ['#71AEC2', '#D58989']

# Criar gráfico de barras interativo
fig = px.bar(data_frame=data, x=data.index, y=data.columns, color_discrete_sequence=cores)

# Configurar título e rótulos dos eixos
fig.update_layout(title='Frequência de doenças cardíacas por categoria de idade',
                  xaxis_title='Categorias de Idade',
                  yaxis_title='Frequencia')

# Exibir o gráfico interativo
fig.show()


# Verificando valores nulos na coluna AlcoholDrinking
df['AlcoholDrinking'].value_counts(dropna=False)

No     190078
NaN    106272
Yes     21673
Name: AlcoholDrinking, dtype: int64


# Verificando valores unicos na coluna AlcoholDrinking
df['AlcoholDrinking'].unique()

array(['No', nan, 'Yes'], dtype=object)


# Preenchendo os valores nulos da coluna AlcoholDrinking
df['AlcoholDrinking'].fillna(value='ZZZ', inplace=True)


df['AlcoholDrinking'].unique()

array(['No', 'ZZZ', 'Yes'], dtype=object)


df['AlcoholDrinking'].value_counts(dropna=False)

No     190078
ZZZ    106272
Yes     21673
Name: AlcoholDrinking, dtype: int64


## # Verificando valores nulos na coluna HeartDisease_FamilyHistory
df['HeartDisease_FamilyHistory'].value_counts(dropna=False)

NaN    282938
No      31853
Yes      3232
Name: HeartDisease_FamilyHistory, dtype: int64


# Preenchendo os valores nulos da coluna HeartDisease_FamilyHistory
df['HeartDisease_FamilyHistory'].fillna(value='XXX', inplace=True)


df['HeartDisease_FamilyHistory'].value_counts(dropna=False)

XXX    282938
No      31853
Yes      3232
Name: HeartDisease_FamilyHistory, dtype: int64


# Matrix transposta do df 
df.head().T


df['GenHealth'].unique()

array(['Very good', 'Fair', 'Good', 'Poor', 'Excellent'], dtype=object)


df['GenHealth'].value_counts(dropna=False)

Very good    113183
Good          92693
Excellent     66395
Fair          34506
Poor          11246
Name: GenHealth, dtype: int64


# Definir a ordem específica das categorias
order = ['Poor', 'Fair', 'Good', 'Very good', 'Excellent']

# Criar um dicionário mapeando cada categoria para seu valor ordinal
mapping = {category: i for i, category in enumerate(order)}

# Aplicar a codificação ordinal na coluna 'GenHealth'
df['GenHealth'] = df['GenHealth'].map(mapping)


df['GenHealth'].unique()

array([3, 1, 2, 0, 4], dtype=int64)


df.head(1).T


df.apply(lambda x: x.nunique(), axis=0)

HeartDisease                     2
BMI                           3606
Smoking                          2
AlcoholDrinking                  3
Stroke                           2
PhysicalHealth                  31
MentalHealth                    31
DiffWalking                      2
Sex                              2
AgeCategory                      4
Race                             6
Diabetic                         4
PhysicalActivity                 2
GenHealth                        5
SleepTime                       24
Asthma                           2
KidneyDisease                    2
SkinCancer                       2
HeartDisease_FamilyHistory       3
State                           51
dtype: int64


df['SleepTime'].value_counts(dropna=False)

7.0     97138
8.0     97054
6.0     66379
5.0     19093
9.0     15970
10.0     7761
4.0      7710
12.0     2196
3.0      1980
2.0       786
1.0       544
11.0      415
14.0      243
16.0      236
15.0      189
18.0      102
13.0       95
20.0       64
24.0       30
17.0       21
22.0        9
19.0        3
23.0        3
21.0        2
Name: SleepTime, dtype: int64


# Definir a ordem específica das categorias (valores únicos em ordem crescente)
order = sorted(df['SleepTime'].unique())

# Criar um dicionário mapeando cada valor para seu valor ordinal (1 a 24)
mapping = {value: i+1 for i, value in enumerate(order)}

# Aplicar a codificação ordinal na coluna 'SleepTime' no DataFrame 'df'
df['SleepTime'] = df['SleepTime'].replace(mapping)


df['SleepTime'].value_counts(dropna=False)

7.0     97138
8.0     97054
6.0     66379
5.0     19093
9.0     15970
10.0     7761
4.0      7710
12.0     2196
3.0      1980
2.0       786
1.0       544
11.0      415
14.0      243
16.0      236
15.0      189
18.0      102
13.0       95
20.0       64
24.0       30
17.0       21
22.0        9
19.0        3
23.0        3
21.0        2
Name: SleepTime, dtype: int64


df['SleepTime'].unique()

array([ 5.,  7.,  8.,  6., 12.,  4.,  9., 10., 15.,  3.,  2.,  1., 16.,
       18., 14., 20., 11., 13., 17., 24., 19., 21., 22., 23.])


df['PhysicalHealth'].value_counts(dropna=False)

0.0     225263
30.0     19422
2.0      14805
1.0      10432
3.0       8585
5.0       7575
10.0      5423
15.0      4990
7.0       4605
4.0       4443
20.0      3197
14.0      2877
6.0       1265
25.0      1155
8.0        919
21.0       625
12.0       603
28.0       444
29.0       203
9.0        180
18.0       166
16.0       135
27.0       124
17.0       109
13.0        91
22.0        89
11.0        84
24.0        67
26.0        66
23.0        46
19.0        35
Name: PhysicalHealth, dtype: int64


# Convertendo a coluna "PhysicalHealth" para o tipo int
df['PhysicalHealth'] = df['PhysicalHealth'].astype(int)


df['MentalHealth'].value_counts(dropna=False)

0.0     204191
30.0     17294
2.0      16413
5.0      14084
10.0     10462
3.0      10409
15.0      9842
1.0       9242
7.0       5505
20.0      5396
4.0       5353
14.0      2041
25.0      1945
6.0       1504
8.0       1091
12.0       755
28.0       509
21.0       350
29.0       316
18.0       211
9.0        203
16.0       151
17.0       127
27.0       125
13.0       110
22.0        98
11.0        83
23.0        67
24.0        66
26.0        59
19.0        21
Name: MentalHealth, dtype: int64


#Convertendo a coluna "MentalHealth" para o tipo int
df['MentalHealth'] = df['MentalHealth'].astype(int)


df.head().T


df.apply(lambda x: x.unique(), axis=0)

HeartDisease                                                             [0, 1]
BMI                           [16.6, 20.34, 26.58, 24.21, 23.71, 28.87, 21.6...
Smoking                                                               [Yes, No]
AlcoholDrinking                                                  [No, ZZZ, Yes]
Stroke                                                                [No, Yes]
PhysicalHealth                [3, 0, 20, 28, 6, 15, 5, 30, 7, 1, 2, 21, 4, 1...
MentalHealth                  [30, 0, 2, 5, 15, 8, 4, 3, 10, 14, 20, 1, 7, 2...
DiffWalking                                                           [No, Yes]
Sex                                                              [Female, Male]
AgeCategory                                                        [2, 3, 1, 0]
Race                          [White, Black, Asian, American Indian/Alaskan ...
Diabetic                      [Yes, No, No, borderline diabetes, Yes (during...
PhysicalActivity                                                      [Yes, No]
GenHealth                                                       [3, 1, 2, 0, 4]
SleepTime                     [5.0, 7.0, 8.0, 6.0, 12.0, 4.0, 9.0, 10.0, 15....
Asthma                                                                [Yes, No]
KidneyDisease                                                         [No, Yes]
SkinCancer                                                            [Yes, No]
HeartDisease_FamilyHistory                                       [No, XXX, Yes]
State                         [MT, VT, WY, DC, PA, AK, KY, DE, CA, NM, WI, V...
dtype: object


#criando a funçao para modificar as colunas com One hoting Encoding

def OHE(dataframe, column_name):
    dummy_dataset = pd.get_dummies(dataframe[column_name], prefix=column_name)
    dataframe = pd.concat([dataframe, dummy_dataset], axis=1)
    dataframe.drop(column_name, axis=1, inplace=True)
    del dummy_dataset

    return dataframe


df = OHE(df, 'Smoking')


df['AlcoholDrinking'].value_counts()

No     190078
ZZZ    106272
Yes     21673
Name: AlcoholDrinking, dtype: int64


df = OHE(df, 'AlcoholDrinking')


df['Stroke'].value_counts()

No     305966
Yes     12057
Name: Stroke, dtype: int64


df = OHE(df, 'Stroke')


df['DiffWalking'].value_counts()

No     273791
Yes     44232
Name: DiffWalking, dtype: int64


df = OHE(df, 'DiffWalking')


df['Sex'].value_counts()

Female    166896
Male      151127
Name: Sex, dtype: int64


df = OHE(df, 'Sex')


df['Race'].value_counts(dropna=False)

White                             243783
Hispanic                           27314
Black                              22840
Other                              10884
Asian                               8026
American Indian/Alaskan Native      5176
Name: Race, dtype: int64


df = OHE(df, 'Race')


df = OHE(df, 'Diabetic')


df = OHE(df, 'PhysicalActivity')


df = OHE(df, 'Asthma')


df = OHE(df, 'KidneyDisease')


df = OHE(df, 'SkinCancer')


df = OHE(df, 'HeartDisease_FamilyHistory')


df.apply(lambda x: x.nunique(), axis=0)

HeartDisease                              2
BMI                                    3606
PhysicalHealth                           31
MentalHealth                             31
AgeCategory                               4
GenHealth                                 5
SleepTime                                24
State                                    51
Smoking_No                                2
Smoking_Yes                               2
AlcoholDrinking_No                        2
AlcoholDrinking_Yes                       2
AlcoholDrinking_ZZZ                       2
Stroke_No                                 2
Stroke_Yes                                2
DiffWalking_No                            2
DiffWalking_Yes                           2
Sex_Female                                2
Sex_Male                                  2
Race_American Indian/Alaskan Native       2
Race_Asian                                2
Race_Black                                2
Race_Hispanic                             2
Race_Other                                2
Race_White                                2
Diabetic_No                               2
Diabetic_No, borderline diabetes          2
Diabetic_Yes                              2
Diabetic_Yes (during pregnancy)           2
PhysicalActivity_No                       2
PhysicalActivity_Yes                      2
Asthma_No                                 2
Asthma_Yes                                2
KidneyDisease_No                          2
KidneyDisease_Yes                         2
SkinCancer_No                             2
SkinCancer_Yes                            2
HeartDisease_FamilyHistory_No             2
HeartDisease_FamilyHistory_XXX            2
HeartDisease_FamilyHistory_Yes            2
dtype: int64


# Remover a coluna "state" do DataFrame
df.drop('State', axis=1, inplace=True)


# iterate over the list to print all unique values of each column in the dataframe
for column in list(df.columns.values):
    print(column, ':', str(df[column].unique()))

HeartDisease : [0 1]
BMI : [16.6  20.34 26.58 ... 62.42 51.46 46.56]
PhysicalHealth : [ 3  0 20 28  6 15  5 30  7  1  2 21  4 10 14 18  8 25 16 29 27 17 24 12
 23 26 22 19  9 13 11]
MentalHealth : [30  0  2  5 15  8  4  3 10 14 20  1  7 24  9 28 16 12 25 17 18 21 29  6
 22 13 23 27 26 11 19]
AgeCategory : [2 3 1 0]
GenHealth : [3 1 2 0 4]
SleepTime : [ 5.  7.  8.  6. 12.  4.  9. 10. 15.  3.  2.  1. 16. 18. 14. 20. 11. 13.
 17. 24. 19. 21. 22. 23.]
Smoking_No : [0 1]
Smoking_Yes : [1 0]
AlcoholDrinking_No : [1 0]
AlcoholDrinking_Yes : [0 1]
AlcoholDrinking_ZZZ : [0 1]
Stroke_No : [1 0]
Stroke_Yes : [0 1]
DiffWalking_No : [1 0]
DiffWalking_Yes : [0 1]
Sex_Female : [1 0]
Sex_Male : [0 1]
Race_American Indian/Alaskan Native : [0 1]
Race_Asian : [0 1]
Race_Black : [0 1]
Race_Hispanic : [0 1]
Race_Other : [0 1]
Race_White : [1 0]
Diabetic_No : [0 1]
Diabetic_No, borderline diabetes : [0 1]
Diabetic_Yes : [1 0]
Diabetic_Yes (during pregnancy) : [0 1]
PhysicalActivity_No : [0 1]
PhysicalActivity_Yes : [1 0]
Asthma_No : [0 1]
Asthma_Yes : [1 0]
KidneyDisease_No : [1 0]
KidneyDisease_Yes : [0 1]
SkinCancer_No : [0 1]
SkinCancer_Yes : [1 0]
HeartDisease_FamilyHistory_No : [1 0]
HeartDisease_FamilyHistory_XXX : [0 1]
HeartDisease_FamilyHistory_Yes : [0 1]


from sklearn import model_selection # model assesment and model selection strategies
from sklearn import metrics # model evaluation metrics


# development = train + test
dev_df_X = df.drop('HeartDisease', axis=1) # development = train + test
dev_df_y = df[['HeartDisease']]


# validation
val_df_X = df.drop('HeartDisease', axis=1)
val_df_y = df[['HeartDisease']]


dev_df_X.head().T


dev_df_y.head().T


X_train, X_test, y_train, y_test = model_selection.train_test_split(
                                        dev_df_X, # X 
                                        dev_df_y, # y
                                        test_size = 0.30, 
                                        random_state = 42
                                     )


X_train.info(verbose=False)

<class 'pandas.core.frame.DataFrame'>
Int64Index: 222616 entries, 171781 to 122586
Columns: 38 entries, BMI to HeartDisease_FamilyHistory_Yes
dtypes: float64(2), int32(2), int64(2), uint8(32)
memory usage: 17.0 MB


X_test.info(verbose=False)

<class 'pandas.core.frame.DataFrame'>
Int64Index: 95407 entries, 304097 to 317388
Columns: 38 entries, BMI to HeartDisease_FamilyHistory_Yes
dtypes: float64(2), int32(2), int64(2), uint8(32)
memory usage: 7.3 MB


X_train.describe().T.head()


X_test.describe().T.head()


y_train.describe().T.head()


y_test.describe().T.head()


from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from sklearn.metrics import accuracy_score
from sklearn.model_selection import cross_val_score


# Criar o modelo Decision Tree Classifier com hiperparâmetros ajustados
DT = DecisionTreeClassifier(max_depth=4, random_state=42)

# Treinar o modelo
DT.fit(X_train, y_train)

# Fazer previsões no conjunto de teste
y_pred1 = DT.predict(X_test)

# Calcular a acurácia do modelo
accuracy = accuracy_score(y_test, y_pred1)
print("Acurácia do modelo Decision Tree Classifier: {:.2f}%".format(accuracy * 100))

# Realizar validação cruzada
cv_scores = cross_val_score(DT, X_train, y_train, cv=5)
print("Acurácia da validação cruzada (média): {:.2f}%".format(cv_scores.mean() * 100))

# Visualizar a árvore de decisão
fig, ax = plt.subplots(figsize=(40, 20))
tree.plot_tree(DT,
               ax=ax,
               fontsize=12,
               proportion=True,
               filled=True,
               feature_names=X_train.columns)
plt.show()

Acurácia do modelo Decision Tree Classifier: 91.47%
Acurácia da validação cruzada (média): 91.47%


from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
from tqdm import tqdm_notebook


# Transformar o array de rótulos em uma matriz unidimensional
y_train = np.ravel(y_train)
y_test = np.ravel(y_test)

# Criar o modelo KNN
KNN = KNeighborsClassifier(n_neighbors=3)  # Defina o número de vizinhos desejado

# Treinar o modelo
KNN.fit(X_train, y_train)

# Fazer previsões no conjunto de teste
y_pred2 = KNN.predict(X_test)

# Calcular a acurácia do modelo
accuracy = accuracy_score(y_test, y_pred2)
print("Acurácia do modelo KNeighbors Classifier é: {:.2f}%".format(accuracy * 100))

# Fazer previsões das probabilidades no conjunto de teste
y_pred_proba = KNN.predict_proba(X_test)[:, 1]

# Calcular a curva ROC
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)
roc_auc = auc(fpr, tpr)

# Plotar a curva ROC
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='Curva ROC (área = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Taxa de Falso Positivo')
plt.ylabel('Taxa de Verdadeiro Positivo')
plt.title('Curva ROC - KNeighbors Classifier')
plt.legend(loc="lower right")
plt.show()

Acurácia do modelo KNeighbors Classifier é: 90.04%


from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, roc_curve, auc


# Criar o modelo Random Forest Classifier
RF = RandomForestClassifier(n_estimators=100)  # Defina o número de estimadores desejado

# Treinar o modelo
RF.fit(X_train, y_train)

# Fazer previsões no conjunto de teste
y_pred3 = RF.predict(X_test)

# Calcular a acurácia do modelo
accuracy = accuracy_score(y_test, y_pred3)
print("Acurácia do modelo: {:.2f}%".format(accuracy * 100))

# Exibir a matriz de confusão
confusion_mat = confusion_matrix(y_test, y_pred3)
print("Matriz de Confusão:")
print(confusion_mat)

# Fazer previsões das probabilidades no conjunto de teste
y_pred_proba = RF.predict_proba(X_test)[:, 1]

# Calcular a curva ROC
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)
roc_auc = auc(fpr, tpr)

# Plotar a curva ROC
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='Curva ROC (área = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Taxa de Falso Positivo')
plt.ylabel('Taxa de Verdadeiro Positivo')
plt.title('Curva ROC')
plt.legend(loc="lower right")
plt.show()

Acurácia do modelo: 90.41%
Matriz de Confusão:
[[85279  1958]
 [ 7195   975]]


from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import accuracy_score, roc_curve, auc


# Criar o modelo Gradient Boosting Classifier
GB = GradientBoostingClassifier()

# Treinar o modelo
GB.fit(X_train, y_train)

# Fazer previsões no conjunto de teste
y_pred4 = GB.predict(X_test)

# Calcular a acurácia do modelo
accuracy = accuracy_score(y_test, y_pred4)
print("Acurácia do modelo Gradient Boosting Classifier: {:.2f}%".format(accuracy * 100))

# Fazer previsões das probabilidades no conjunto de teste
y_pred_proba = GB.predict_proba(X_test)[:, 1]

# Calcular a curva ROC
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)
roc_auc = auc(fpr, tpr)

# Plotar a curva ROC
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='Curva ROC (área = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Taxa de Falso Positivo')
plt.ylabel('Taxa de Verdadeiro Positivo')
plt.title('Curva ROC - Gradient Boosting Classifier')
plt.legend(loc="lower right")
plt.show()

Acurácia do modelo Gradient Boosting Classifier: 91.59%


from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
from sklearn.preprocessing import StandardScaler


# Pré-processar os dados - Padronizar os recursos
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Criar o modelo de regressão logística
LR = LogisticRegression()

# Treinar o modelo usando os dados de treinamento
LR.fit(X_train, y_train)

# Fazer previsões usando os dados de teste
y_pred5 = LR.predict(X_test)

# Calcular a acurácia do modelo
accuracy = accuracy_score(y_test, y_pred5)
print("Acurácia:", accuracy)

# Calcular outras métricas de avaliação
print("Relatório de Classificação:")
print(classification_report(y_test, y_pred5))

# Fazer previsões das probabilidades no conjunto de teste
y_pred_proba = LR.predict_proba(X_test)[:, 1]

# Calcular a curva ROC
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)
roc_auc = auc(fpr, tpr)

# Plotar a curva ROC
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='Curva ROC (área = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Taxa de Falso Positivo')
plt.ylabel('Taxa de Verdadeiro Positivo')
plt.title('Curva ROC - Regressão Logística')
plt.legend(loc="lower right")
plt.show()

Acurácia: 0.915603676879055
Relatório de Classificação:
              precision    recall  f1-score   support

           0       0.92      0.99      0.96     87237
           1       0.54      0.11      0.18      8170

    accuracy                           0.92     95407
   macro avg       0.73      0.55      0.57     95407
weighted avg       0.89      0.92      0.89     95407


final_data = pd.DataFrame ({ 'MODELOS': [ 'DT', 'KNN', 'RF', 'GB', 'LR'], 
                                        'ACC': [accuracy_score(y_test, y_pred1), 
                                                accuracy_score(y_test, y_pred2),
                                                accuracy_score(y_test, y_pred3),
                                                accuracy_score(y_test, y_pred4),
                                                accuracy_score(y_test, y_pred5)]})
final_data


RANDOM_STATE = 42
n_estimators = 50
max_depth = 5

models = [ 
    ('DT', DecisionTreeClassifier(max_depth=max_depth, random_state=42)),
    ('KNN', KNeighborsClassifier()),
    ('RF', RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth, random_state=RANDOM_STATE)),
    ('GB', GradientBoostingClassifier(n_estimators=n_estimators, max_depth=max_depth, random_state=RANDOM_STATE)),
    ('LR', LogisticRegression(random_state=RANDOM_STATE))
]


plt.clf()
for model in models:
    model_name = model[0]
    model_instance = model[1]
    model_instance.fit(X_train, np.ravel(y_train))
    predictions = model_instance.predict_proba(X_test)[:,1]
    auc_score = metrics.roc_auc_score(y_test, predictions)
    print('ROC AUC Score for {}: {}'.format(model_name, auc_score))
    fpr, tpr, _ = metrics.roc_curve(y_test, predictions)
    plt.plot(fpr, tpr, label='ROC Curve for {} - Area: {:2f}'.format(model_name, auc_score))
plt.plot([0, 1], [0, 1], color='gray', linestyle='--')
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.legend(loc="lower right")
plt.title('ROC curve')
plt.show()

ROC AUC Score for DT: 0.8186580594634724
ROC AUC Score for KNN: 0.6969406951439943
ROC AUC Score for RF: 0.8281936835808315
ROC AUC Score for GB: 0.8410159831483136
ROC AUC Score for LR: 0.8384305025425678


#%%time
#profile = ProfileReport(df, title="Pandas Profiling Report")

#profile.to_file("reports/EDA.html")

	count	mean	std	min	25%	50%	75%	max
BMI	95407.0	28.314242	6.356699	12.02	24.0	27.32	31.45	92.53
PhysicalHealth	95407.0	3.380381	7.957179	0.00	0.0	0.00	2.00	30.00
MentalHealth	95407.0	3.922249	7.986935	0.00	0.0	0.00	3.00	30.00
AgeCategory	95407.0	1.513746	0.943889	0.00	1.0	2.00	2.00	3.00
GenHealth	95407.0	2.594317	1.041420	0.00	2.0	3.00	3.00	4.00

#	Feature	Description
1	HeartDisease	Respondents that have ever reported having coronary heart disease (CHD) or myocardial infarction (MI)
2	BMI	Body Mass Index (BMI)
3	Smoking	Have you smoked at least 100 cigarettes in your entire life? [Note: 5 packs = 100 cigarettes]
4	AlcoholDrinking	Heavy drinkers (adult men having more than 14 drinks per week and adult women having more than 7 drinks per week
5	Stroke	(Ever told) (you had) a stroke?
6	PhysicalHealth	Now thinking about your physical health, which includes physical illness and injury, for how many days during the past 30
7	MentalHealth	Thinking about your mental health, for how many days during the past 30 days was your mental health not good?
8	DiffWalking	Do you have serious difficulty walking or climbing stairs?
9	Sex	Are you male or female?
10	AgeCategory	Fourteen-level age category
11	Race	Imputed race/ethnicity value
12	Diabetic	(Ever told) (you had) diabetes?
13	PhysicalActivity	Adults who reported doing physical activity or exercise during the past 30 days other than their regular job
14	GenHealth	Would you say that in general your health is...
15	SleepTime	On average, how many hours of sleep do you get in a 24-hour period?
16	Asthma	(Ever told) (you had) asthma?
17	KidneyDisease	Not including kidney stones, bladder infection or incontinence, were you ever told you had kidney disease?
18	SkinCancer	(Ever told) (you had) skin cancer?
19	HeartDisease_FamilyHistory	Do you have family history of heart disease?
20	State	US sate (residency)

	HeartDisease	BMI	Smoking	AlcoholDrinking	Stroke	PhysicalHealth	MentalHealth	DiffWalking	Sex	AgeCategory	Race	Diabetic	PhysicalActivity	GenHealth	SleepTime	Asthma	KidneyDisease	SkinCancer	HeartDisease_FamilyHistory	State
0	No	16.60	Yes	No	No	3.0	30.0	No	Female	55-59	White	Yes	Yes	Very good	5.0	Yes	No	Yes	No	MT
1	No	20.34	No	NaN	Yes	0.0	0.0	No	Female	80 or older	White	No	Yes	Very good	7.0	No	No	No	NaN	VT
2	No	26.58	Yes	NaN	No	20.0	30.0	No	Male	65-69	White	Yes	Yes	Fair	8.0	Yes	No	No	NaN	WY
3	No	24.21	No	NaN	No	0.0	0.0	No	Female	75-79	White	No	No	Good	6.0	No	No	Yes	No	VT
4	No	23.71	No	No	No	28.0	0.0	Yes	Female	40-44	White	No	Yes	Very good	8.0	No	No	No	NaN	DC
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
319790	Yes	27.41	Yes	No	No	7.0	0.0	Yes	Male	60-64	Hispanic	Yes	No	Fair	6.0	Yes	No	No	NaN	AZ
319791	No	29.84	Yes	NaN	No	0.0	0.0	No	Male	35-39	Hispanic	No	Yes	Very good	5.0	Yes	No	No	No	NH
319792	No	24.24	No	No	No	0.0	0.0	No	Female	45-49	Hispanic	No	Yes	Good	6.0	No	No	No	NaN	DE
319793	No	32.81	No	NaN	No	0.0	0.0	No	Female	25-29	Hispanic	No	No	Good	12.0	No	No	No	NaN	UT
319794	No	46.56	No	NaN	No	0.0	0.0	No	Female	80 or older	Hispanic	No	Yes	Good	8.0	No	No	No	NaN	OR

	count	unique	top	freq
HeartDisease	319541	2	No	292168
Smoking	319541	2	No	187692
AlcoholDrinking	212788	2	No	191014
Stroke	318429	2	No	306360
DiffWalking	319541	2	No	275131
Sex	319541	2	Female	167696
AgeCategory	319541	14	65-69	34108
Race	319541	6	White	244962
Diabetic	319541	4	No	269403
PhysicalActivity	319541	2	Yes	247705
GenHealth	319541	5	Very good	113727
Asthma	319541	2	No	276671
KidneyDisease	319541	2	No	307762
SkinCancer	319192	2	No	289377
HeartDisease_FamilyHistory	35261	2	No	32006
State	319541	51	OH	6417

	0	1	2	3	4
HeartDisease	0	0	0	0	0
BMI	16.6	20.34	26.58	24.21	23.71
Smoking	Yes	No	Yes	No	No
AlcoholDrinking	No	ZZZ	ZZZ	ZZZ	No
Stroke	No	Yes	No	No	No
PhysicalHealth	3.0	0.0	20.0	0.0	28.0
MentalHealth	30.0	0.0	30.0	0.0	0.0
DiffWalking	No	No	No	No	Yes
Sex	Female	Female	Male	Female	Female
AgeCategory	2	3	2	3	1
Race	White	White	White	White	White
Diabetic	Yes	No	Yes	No	No
PhysicalActivity	Yes	Yes	Yes	No	Yes
GenHealth	Very good	Very good	Fair	Good	Very good
SleepTime	5.0	7.0	8.0	6.0	8.0
Asthma	Yes	No	Yes	No	No
KidneyDisease	No	No	No	No	No
SkinCancer	Yes	No	No	Yes	No
HeartDisease_FamilyHistory	No	XXX	XXX	No	XXX
State	MT	VT	WY	VT	DC

	count	mean	std	min	25%	50%	75%	max
BMI	222616.0	28.335417	6.377846	12.02	24.03	27.34	31.45	119.0
PhysicalHealth	222616.0	3.372188	7.952641	0.00	0.00	0.00	2.00	30.0
MentalHealth	222616.0	3.891683	7.944438	0.00	0.00	0.00	3.00	30.0
AgeCategory	222616.0	1.509339	0.943634	0.00	1.00	2.00	2.00	3.0
GenHealth	222616.0	2.594176	1.043680	0.00	2.00	3.00	3.00	4.0

	MODELOS	ACC
0	DT	0.914713
1	KNN	0.900437
2	RF	0.904064
3	GB	0.915950
4	LR	0.915604

Heart Deseases Prediction¶

Table of Contents¶

Dados¶

Data Understanding ¶

Visualização direta dos dados¶

Shape ¶

Columns ¶

List of numerical features ¶

List of categorical features ¶

Descriptive statistics¶

Number/fractions of null values¶

Visualização univariada de recursos categóricos¶

HeartDisease ¶

Proporção de doenças cardíacas a partir dos dados¶

BMI ¶

SkinCancer ¶

Stroke ¶

Função heart_Disease ¶

AgeCategory ¶

Alcohol Drinking ¶

Heart Disease Family History ¶

Codificação Ordinal ¶

GenHealth¶

Sleep Time¶

PhysicalHealth¶

MentalHealth¶

Codificação One-Hot ¶

Get Dummies¶

Smoking¶

AlcoholDrinking¶

Stroke¶

DiffWalking¶

Sex¶

Race¶

Diabetic¶

PhysicalActivity¶

Asthma¶

KidneyDisease¶

SkinCancer¶

HeartDisease_FamilyHistory¶

Drop coluna State¶

Valores Exclusivos por coluna¶

Modelling ¶

Determine validation strategy (Random Holdout) & partition policy for test set (random)¶

Model definition ¶

DecisionTreeClassifier¶

KNeighbors Classifier¶

RandomForestClassifier¶

Gradient Boosting Classifier¶

Logistic Regression¶

FINAL MODEL COMPARISON ¶

Visualização direta dos dados ¶

Descriptive statistics ¶

Number/fractions of null values ¶

Visualização univariada de recursos categóricos ¶